Accurate max-margin training for structured output spaces

Journal of Machine Learning Research, 2014

We consider a framework for structured prediction based on search in the space of complete structured outputs. Given a structured input, an output is produced by running a timebounded search procedure guided by a learned cost function, and then returning the least cost output uncovered during the search. This framework can be instantiated for a wide range of search spaces and search procedures, and easily incorporates arbitrary structuredprediction loss functions. In this paper, we make two main technical contributions. First, we describe a novel approach to automatically defining an effective search space over structured outputs, which is able to leverage the availability of powerful classification learning algorithms. In particular, we define the limited-discrepancy search space and relate the quality of that space to the quality of learned classifiers. We also define a sparse version of the search space to improve the efficiency of our overall approach. Second, we give a generic cost function learning approach that is applicable to a wide range of search procedures. The key idea is to learn a cost function that attempts to mimic the behavior of conducting searches guided by the true loss function. Our experiments on six benchmark domains show that a small amount of search in limited discrepancy search space is often sufficient for significantly improving on state-of-the-art structured-prediction performance. We also demonstrate significant speed improvements for our approach using sparse search spaces with little or no loss in accuracy.

ArXiv, 2020

A powerful and flexible approach to structured prediction consists in embedding the structured objects to be predicted into a feature space of possibly infinite dimension by means of output kernels, and then, solving a regression problem in this output space. A prediction in the original space is computed by solving a pre-image problem. In such an approach, the embedding, linked to the target loss, is defined prior to the learning phase. In this work, we propose to jointly learn a finite approximation of the output embedding and the regression function into the new feature space. For that purpose, we leverage a priori information on the outputs and also unexploited unsupervised output data, which are both often available in structured prediction problems. We prove that the resulting structured predictor is a consistent estimator, and derive an excess risk bound. Moreover, the novel structured prediction tool enjoys a significantly smaller computational complexity than former output ...

2012

Abstract: Structured prediction is the cornerstone of several machine learning applications. Unfortunately, in structured prediction settings with expressive inter-variable interactions, exact inference-based learning algorithms, eg Structural SVM, are often intractable. We present a new way, Decomposed Learning (DecL), which performs efficient learning by restricting the inference step to a limited part of the structured spaces.

A common obstacle preventing the rapid deployment of supervised machine learning algorithms is the lack of labeled training data. This is particularly expensive to obtain for structured prediction tasks, where each training instance may have multiple, interacting labels, all of which must be correctly annotated for the instance to be of use to the learner. Traditional active learning addresses this problem by optimizing the order in which the examples are labeled to increase learning efficiency. However, this approach does not consider the difficulty of labeling each example, which can vary widely in structured prediction tasks. For example, the labeling predicted by a partially trained system may be easier to correct for some instances than for others. We propose a new active learning paradigm which reduces not only how many instances the annotator must label, but also how difficult each instance is to annotate. The system leverages information from partially correct predictions to efficiently solicit annotations from the user. We validate this active learning framework in an interactive information extraction system, reducing the total number of annotation actions by 22%.

2012

We consider a framework for structured prediction based on search in the space of complete structured outputs. Given a structured input, an output is produced by running a time-bounded search procedure guided by a learned cost function, and then returning the least cost output uncovered during the search. This framework can be instantiated for a wide range of search spaces and search procedures, and easily incorporates arbitrary structured-prediction loss functions. In this paper, we make two main technical contributions. First, we define the limited-discrepancy search space over structured outputs, which is able to leverage powerful classification learning algorithms to improve the search space quality. Second, we give a generic cost function learning approach, where the key idea is to learn a cost function that attempts to mimic the behavior of conducting searches guided by the true loss function. Our experiments on six benchmark domains demonstrate that using our framework with only a small amount of search is sufficient for significantly improving on state-of-the-art structuredprediction performance.

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016

Images of scenes have various objects as well as abundant attributes, and diverse levels of visual categorization are possible. A natural image could be assigned with finegrained labels that describe major components, coarsegrained labels that depict high level abstraction, or a set of labels that reveal attributes. Such categorization at different concept layers can be modeled with label graphs encoding label information. In this paper, we exploit this rich information with a state-of-art deep learning framework, and propose a generic structured model that leverages diverse label relations to improve image classification performance. Our approach employs a novel stacked label prediction neural network, capturing both inter-level and intra-level label semantics. We evaluate our method on benchmark image datasets, and empirical results illustrate the efficacy of our model.

2019

I feel truly privileged to have worked with my supervisors, Laurent Kneip, Jose Alvarez, and specifically Lars Petersson. Thank you, Lars, for your encouragement and inspiration. You always supported me wholeheartedly in my hardest times throughout this journey. Your technical brilliance, professional standards and research insight make you an ideal mentor.

arXiv (Cornell University), 2016

A key problem in structured output prediction is direct optimization of the task reward function that matters for test evaluation. This paper presents a simple and computationally efficient approach to incorporate task reward into a maximum likelihood framework. By establishing a link between the log-likelihood and expected reward objectives, we show that an optimal regularized expected reward is achieved when the conditional distribution of the outputs given the inputs is proportional to their exponentiated scaled rewards. Accordingly, we present a framework to smooth the predictive probability of the outputs using their corresponding rewards. We optimize the conditional log-probability of augmented outputs that are sampled proportionally to their exponentiated scaled rewards. Experiments on neural sequence to sequence models for speech recognition and machine translation show notable improvements over a maximum likelihood baseline by using reward augmented maximum likelihood (RAML), where the rewards are defined as the negative edit distance between the outputs and the ground truth labels.

2012

In this paper we propose a new approach for semi-supervised structured output learning. Our approach uses relaxed labeling on unlabeled data to deal with the combinatorial nature of the label space and further uses domain constraints to guide the learning. Since the overall objective is non-convex, we alternate between the optimization of the model parameters and the label distribution of unlabeled data. The alternating optimization coupled with deterministic annealing helps us achieve better local optima and as a result our approach leads to better constraint satisfaction during inference. Experimental results on sequence labeling benchmarks show superior performance of our approach compared to Constraint Driven Learning (CoDL) and Posterior Regularization (PR).

2007

Abstract We consider the problem of training a conditional random field (CRF) to maximize per-label predictive accuracy on a training set, an approach motivated by the principle of empirical risk minimization. We give a gradient-based procedure for minimizing an arbitrarily accurate approximation of the empirical risk under a Hamming loss function.